FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386759896> ?p ?o ?g. }

• W4386759896 endingPage "126791" @default.
• W4386759896 startingPage "126791" @default.
• W4386759896 abstract "In recent years, deep learning models have shown their advantages in neuroimage analysis, such as brain disease diagnosis. Unfortunately, it is usually difficult to acquire numerous brain networks at a single centralized site to effectively train a high-quality deep learning model. To address this issue, federated learning (FL) has gained popularity in brain disease diagnosis, which allows deep learning models to be trained without centralizing data. However, most FL-based works might still face two following challenges. Firstly, the high-dimensional features of brain networks are often far larger than sample size, which might lead to poor performance due to the curse of dimensionality. Secondly, differences in data distributions across different sites can impact the communication efficiency and performance of FL models. To overcome these challenges, we design a novel FL framework for diagnosing brain disorders, named FedBrain. Firstly, FedBrain proposes data augmentation based on L1 regularization to select significant features shared by all clients. The domain alignment loss based on the maximum mean discrepancy criterion is introduced to minimize differences in the marginal and conditional distributions between local clients. Furthermore, FedBrain proposes a personalized predictor based on mixture of experts to adapt to different clients, using a global and private predictor as two experts. Eventually, FedBrain integrates the above modules with differential privacy and homomorphic encryption into a unified FL framework. Experimental results on the Autism Brain Imaging Data Exchange (ABIDE) dataset demonstrate its effectiveness and robustness, which shows that FedBrain can reduce the communication burden of FL and achieve the highest average accuracy of 79% against other counterparts." @default.
• W4386759896 created "2023-09-16" @default.
• W4386759896 creator A5027098586 @default.
• W4386759896 creator A5057055806 @default.
• W4386759896 creator A5062755510 @default.
• W4386759896 creator A5073839526 @default.
• W4386759896 creator A5082013146 @default.
• W4386759896 creator A5086631373 @default.
• W4386759896 date "2023-11-01" @default.
• W4386759896 modified "2023-10-15" @default.
• W4386759896 title "FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis" @default.
• W4386759896 cites W1536680647 @default.
• W4386759896 cites W1974316717 @default.
• W4386759896 cites W1978408307 @default.
• W4386759896 cites W1990385855 @default.
• W4386759896 cites W1994341528 @default.
• W4386759896 cites W2011695670 @default.
• W4386759896 cites W2049228309 @default.
• W4386759896 cites W2058046532 @default.
• W4386759896 cites W2072522618 @default.
• W4386759896 cites W2079426910 @default.
• W4386759896 cites W2098740506 @default.
• W4386759896 cites W2140049038 @default.
• W4386759896 cites W2152346792 @default.
• W4386759896 cites W2526511911 @default.
• W4386759896 cites W2592929672 @default.
• W4386759896 cites W2752558629 @default.
• W4386759896 cites W2770349518 @default.
• W4386759896 cites W2782495832 @default.
• W4386759896 cites W2900580671 @default.
• W4386759896 cites W2904807663 @default.
• W4386759896 cites W2919115771 @default.
• W4386759896 cites W2944352397 @default.
• W4386759896 cites W2956451617 @default.
• W4386759896 cites W2987509417 @default.
• W4386759896 cites W2990504128 @default.
• W4386759896 cites W2998312380 @default.
• W4386759896 cites W3001336471 @default.
• W4386759896 cites W3006829355 @default.
• W4386759896 cites W3016632787 @default.
• W4386759896 cites W3037254739 @default.
• W4386759896 cites W3040685212 @default.
• W4386759896 cites W3042006926 @default.
• W4386759896 cites W3086590218 @default.
• W4386759896 cites W3093225483 @default.
• W4386759896 cites W3095114157 @default.
• W4386759896 cites W3102324028 @default.
• W4386759896 cites W3104576595 @default.
• W4386759896 cites W3137011626 @default.
• W4386759896 cites W3144859282 @default.
• W4386759896 cites W3157331556 @default.
• W4386759896 cites W3175307072 @default.
• W4386759896 cites W3182158470 @default.
• W4386759896 cites W3199008037 @default.
• W4386759896 cites W4223465279 @default.
• W4386759896 cites W4294106961 @default.
• W4386759896 cites W4376866854 @default.
• W4386759896 doi "https://doi.org/10.1016/j.neucom.2023.126791" @default.
• W4386759896 hasPublicationYear "2023" @default.
• W4386759896 type Work @default.
• W4386759896 citedByCount "0" @default.
• W4386759896 crossrefType "journal-article" @default.
• W4386759896 hasAuthorship W4386759896A5027098586 @default.
• W4386759896 hasAuthorship W4386759896A5057055806 @default.
• W4386759896 hasAuthorship W4386759896A5062755510 @default.
• W4386759896 hasAuthorship W4386759896A5073839526 @default.
• W4386759896 hasAuthorship W4386759896A5082013146 @default.
• W4386759896 hasAuthorship W4386759896A5086631373 @default.
• W4386759896 hasConcept C104317684 @default.
• W4386759896 hasConcept C108583219 @default.
• W4386759896 hasConcept C111030470 @default.
• W4386759896 hasConcept C111919701 @default.
• W4386759896 hasConcept C119857082 @default.
• W4386759896 hasConcept C124101348 @default.
• W4386759896 hasConcept C148730421 @default.
• W4386759896 hasConcept C154945302 @default.
• W4386759896 hasConcept C15744967 @default.
• W4386759896 hasConcept C158338273 @default.
• W4386759896 hasConcept C185592680 @default.
• W4386759896 hasConcept C2780586970 @default.
• W4386759896 hasConcept C41008148 @default.
• W4386759896 hasConcept C55493867 @default.
• W4386759896 hasConcept C63479239 @default.
• W4386759896 hasConcept C77805123 @default.
• W4386759896 hasConceptScore W4386759896C104317684 @default.
• W4386759896 hasConceptScore W4386759896C108583219 @default.
• W4386759896 hasConceptScore W4386759896C111030470 @default.
• W4386759896 hasConceptScore W4386759896C111919701 @default.
• W4386759896 hasConceptScore W4386759896C119857082 @default.
• W4386759896 hasConceptScore W4386759896C124101348 @default.
• W4386759896 hasConceptScore W4386759896C148730421 @default.
• W4386759896 hasConceptScore W4386759896C154945302 @default.
• W4386759896 hasConceptScore W4386759896C15744967 @default.
• W4386759896 hasConceptScore W4386759896C158338273 @default.
• W4386759896 hasConceptScore W4386759896C185592680 @default.
• W4386759896 hasConceptScore W4386759896C2780586970 @default.
• W4386759896 hasConceptScore W4386759896C41008148 @default.
• W4386759896 hasConceptScore W4386759896C55493867 @default.

• next